© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-1B-IT
    5. 13-GEMMASCOPE-2-RES-16K
    7. 8366
    Prev
    Next
    INDEX
    Explanations

    Data scaling, stable, root, sized

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-1b-it/resid_post/layer_13_width_16k_l0_medium
    Prompts (Dashboard)
    238,145 prompts, 512 tokens each
    Dataset (Dashboard)
    lmsys + oasst1
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    గం
    1.16
    izal
    1.04
     Larger
    1.03
    ized
    1.03
    ness
    1.03
    ਡ
    1.02
     emerg
    0.99
    izacji
    0.98
     spout
    0.98
     larger
    0.97
    POSITIVE LOGITS
     bu
    0.90
    Customer
    0.89
    ากาศ
    0.87
     Customer
    0.85
    VIA
    0.84
     Warhammer
    0.84
     एक्सचेंज
    0.83
     astrology
    0.82
     тре
    0.81
    辞
    0.81
    Activations Density 0.000%

    No Known Activations